Machine Unlearning of Traffic State Estimation and Prediction
It addresses privacy and regulatory compliance issues for intelligent transportation systems, though it appears incremental as it applies an existing unlearning concept to a specific domain.
This study tackled the problem of privacy and data freshness in traffic state estimation and prediction by introducing a machine unlearning paradigm that allows models to selectively forget sensitive, poisoned, or outdated data, aiming to enhance trustworthiness and reliability.
Data-driven traffic state estimation and prediction (TSEP) relies heavily on data sources that contain sensitive information. While the abundance of data has fueled significant breakthroughs, particularly in machine learning-based methods, it also raises concerns regarding privacy, cybersecurity, and data freshness. These issues can erode public trust in intelligent transportation systems. Recently, regulations have introduced the "right to be forgotten", allowing users to request the removal of their private data from models. As machine learning models can remember old data, simply removing it from back-end databases is insufficient in such systems. To address these challenges, this study introduces a novel learning paradigm for TSEP-Machine Unlearning TSEP-which enables a trained TSEP model to selectively forget privacy-sensitive, poisoned, or outdated data. By empowering models to "unlearn," we aim to enhance the trustworthiness and reliability of data-driven traffic TSEP.